© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 14155
    Prev
    Next
    INDEX
    Explanations

    locations or settings within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    commas used frequently in lists or descriptive sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orem
    -0.81
    isi
    -0.73
    utenant
    -0.73
    nil
    -0.68
    ISE
    -0.66
    unct
    -0.66
    tains
    -0.65
    +++
    -0.65
    ukong
    -0.64
    ipient
    -0.64
    POSITIVE LOGITS
     hoping
    1.35
     preferring
    1.23
     prompting
    1.15
     risking
    1.10
     fearing
    1.07
     creating
    1.06
     exchanging
    1.04
     culminating
    1.04
     forcing
    1.03
     seeking
    1.02
    Activations Density 0.357%

    No Known Activations